Svdnet For Pedestrian Retrieval

Abstract

This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis. It is observed that the weight vectors are usually highly correlated. This problem leads to correlations among entries of the FC descriptor, and compromises the retrieval performance based on the Euclidean distance. To address the problem, this paper proposes to optimize the deep representation learning process with Singular Vector Decomposition (SVD). Specifically, with the restraint and relaxation iteration (RRI) training scheme, we are able to iteratively integrate the orthogonality constraint in CNN training, yielding the so-called SVDNet. We conduct experiments on the Market-1501, CUHK03, and Duke datasets, and show that RRI effectively reduces the correlation among the projection vectors, produces more discriminative FC descriptors, and

Stats

• citations622
• S2 citations—
• github stars0
• HF likes0
• heat score20.96
• arxiv keysun2017svdnet

Related papers

• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32
• Auto-reid: Searching For A Part-aware Convnet For Person Re-identification (2019)17.27
• Structured Deep Hashing With Convolutional Neural Networks For Fast Person Re-identification (2017)12.87
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Ensemble Feature For Person Re-identification (2019)0.00
• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71